Marketing method and system based on user behavior analysis and program product

Abstract

The invention belongs to the technical field of data analysis, and particularly discloses a marketing method and system based on user behavior analysis and a program product, and the method comprises the steps: carrying out the multi-dimensional behavior data analysis of a historical behavior data set of a target user for various products in a set time period, and determining the reference indexes of the target user for various products; and then the dynamic recommendation indexes of various products are comprehensively counted for the target user to screen out marketing recommendation products, and finally the marketing recommendation product information is pushed to the target user, so that accurate product marketing recommendation is realized. According to the method, time period dynamic analysis is performed by integrating the multi-dimensional behavior data of the user, so that the product preference characteristics of the user in a specific time period can be fully controlled, the interested products of the user are mastered, the product recommendation accuracy for the user is effectively improved, and the recommendation conversion rate is remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and particularly relates to a marketing method, system and program product based on user behavior analysis. Background Art

[0002] User marketing is a user-centered marketing method, that is, a proactive marketing method carried out by a platform using the information of existing users to increase the sales expenditure of existing users and enhance customer value. The core of user marketing is user-centered, and it improves user value and platform loyalty through data analysis, stratification strategies and interaction mechanisms. User marketing optimizes the user experience, attracts users to make repeat purchases, and achieves a win-win situation of word-of-mouth and revenue. Most of the existing platform user marketing methods rely on user portrait information or single behavior data of users (such as search records or purchase records), ignoring the demand tendencies reflected by the multi-dimensional behavior characteristics of users during corresponding periods, and unable to reflect the dynamic changes in user behavior patterns, resulting in low accuracy of product recommendations for users and poor user experience. Summary of the Invention

[0003] The purpose of the present invention is to provide a marketing method, system and program product based on user behavior analysis to solve the above problems existing in the prior art.

[0004] To achieve the above purpose, the present invention adopts the following technical solutions: In the first aspect, a marketing method based on user behavior analysis is provided, including: Collecting a historical behavior data set of a target user for various products within a set time period, where the historical behavior data set includes historical search term frequency data, historical browsing duration data, historical purchase price data, and historical purchase frequency data; Determining a search frequency factor for each type of product according to the historical search term frequency data of the target user for each type of product, and calculating a search frequency index parameter for each type of product by using the search frequency factor of each type of product; Determining a browsing duration factor for each type of product according to the historical browsing duration data of the target user for each type of product, and calculating a browsing duration index parameter for each type of product by using the browsing duration factor of each type of product; Determining a purchase price factor for each type of product according to the historical purchase price data of the target user for each type of product, and calculating a price preference index parameter for each type of product by using the purchase price factor of each type of product; Determining a purchase frequency factor for each type of product according to the historical purchase frequency data of the target user for each type of product, and calculating a purchase tendency index parameter for each type of product by using the purchase frequency factor of each type of product; Calculate the dynamic recommendation index of various products based on search frequency index parameters, browsing duration index parameters, price preference index parameters, and purchase tendency index parameters; Screen marketing recommended products from various products according to the dynamic recommendation index of various products, and push the product information of the marketing recommended products to the target users.

[0005] In a possible design, the method for determining the search frequency factor of various products according to the historical search term frequency data of the target user for various products and calculating the search frequency index parameter of various products by using the search frequency factor of various products includes: Determine the ratio of the historical search term frequency data of the target user for a certain type of product to the sum of the historical search term frequency data of all types of products, and use this ratio as the search frequency factor of the certain type of product; Multiply the search frequency factor of each certain type of product by the set search index coefficient to obtain the search frequency index parameter of various products.

[0006] In a possible design, the method for determining the browsing duration factor of various products according to the historical browsing duration data of the target user for various products and calculating the browsing duration index parameter of various products by using the browsing duration factor of various products includes: Determine the ratio of the historical browsing duration data of the target user for a certain type of product to the sum of the historical browsing duration data of all types of products, and use this ratio as the browsing duration factor of the certain type of product; Substitute the browsing duration factor of various products into the preset browsing duration index parameter formula for calculation to obtain the browsing duration index parameter of various products. The browsing duration index parameter formula is:

[0007] where, i represents the product category number, T i represents the browsing duration index parameter of the i-th type of product, t i represents the browsing duration factor of the i-th type of product, τ is the set duration index coefficient, and tanh is the hyperbolic tangent function.

[0008] In a possible design, the method for determining the purchase price factor of various products according to the historical purchase price data of the target user for various products and calculating the price preference index parameter of various products by using the purchase price factor of various products includes: Determine the platform benchmark price data of various products, and use the absolute value of the difference between the historical purchase price data of the target user for a certain type of product and the platform benchmark price data of the certain type of product as the purchase price factor of the certain type of product; Substitute the purchase price factors of various products into the pre-set price preference index parameter formula for calculation to obtain the price preference index parameters of various products. The price preference index parameter formula is as follows:

[0009] where i represents the product category number, P i represents the price preference index parameter of the i-th type of product, p i represents the purchase price factor of the i-th type of product, and σ is the set price index coefficient.

[0010] In a possible design, the method for determining the purchase frequency factors of various products according to the historical purchase times data of the target user for various products and calculating the purchase propensity index parameters of various products using the purchase frequency factors of various products includes: Determine the ratio of the historical purchase times data of the target user for a certain type of product to the sum of the historical purchase times data of all types of products, and use this ratio as the purchase frequency factor of the certain type of product; Substitute the purchase frequency factors of the target user for various products into the pre-set purchase propensity index parameter formula for calculation to obtain the purchase propensity index parameters of various products. The purchase propensity index parameter formula is as follows:

[0011] where i represents the product category number, N i represents the purchase propensity index parameter of the i-th type of product, n i represents the purchase frequency factor of the i-th type of product, and δ is the set frequency index coefficient.

[0012] In a possible design, the method for calculating the dynamic recommendation index of various products based on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase propensity index parameter includes: Perform weighted summation on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase propensity index parameter of a certain type of product to obtain the dynamic recommendation index of the certain type of product.

[0013] In a possible design, the method for screening marketing recommendation products from various products according to the dynamic recommendation index of various products includes: Screen several types of products with the highest dynamic recommendation index from various products as marketing recommendation products.

[0014] In a second aspect, a marketing system based on user behavior analysis is provided, including a data collection unit, a first determination unit, a second determination unit, a third determination unit, a fourth determination unit, an index calculation unit, and a marketing push unit, where: A data collection unit for collecting a historical behavior data set of a target user for various products within a set time period, where the historical behavior data set includes historical search term frequency data, historical browsing duration data, historical purchase price data, and historical purchase frequency data; A first determination unit for determining a search frequency factor for various products based on the historical search term frequency data of the target user for various products, and calculating a search frequency index parameter for various products using the search frequency factors of various products; A second determination unit for determining a browsing duration factor for various products based on the historical browsing duration data of the target user for various products, and calculating a browsing duration index parameter for various products using the browsing duration factors of various products; A third determination unit for determining a purchase price factor for various products based on the historical purchase price data of the target user for various products, and calculating a price preference index parameter for various products using the purchase price factors of various products; A fourth determination unit for determining a purchase frequency factor for various products based on the historical purchase frequency data of the target user for various products, and calculating a purchase tendency index parameter for various products using the purchase frequency factors of various products; An index calculation unit for calculating a dynamic recommendation index for various products based on the search frequency index parameter, the browsing duration index parameter, the price preference index parameter, and the purchase tendency index parameter; A marketing push unit for screening marketing recommended products from various products according to the dynamic recommendation index of various products, and pushing the product information of the marketing recommended products to the target user.

[0015] In a third aspect, a marketing system based on user behavior analysis is provided, including: A memory for storing instructions; A processor for reading the instructions stored in the memory and executing the method according to any one of the above in the first aspect.

[0016] In a fourth aspect, a computer-readable storage medium is provided, where instructions are stored on the computer-readable storage medium, and when the instructions are run on a computer, the computer executes the method according to any one of the above in the first aspect. At the same time, a computer program product is also provided, and when the computer program product is run on a computer, it executes the method according to any one of the above in the first aspect.

[0017] Beneficial effects: By collecting the historical behavior data sets of a target user for various products within a set time period and conducting multi-dimensional behavior data analysis, the present invention determines various reference indicators of the target user for various products, and then comprehensively calculates the dynamic recommendation index of various products for the target user to screen out marketing recommended products. Finally, the marketing recommended product information is pushed to the target user, achieving accurate product marketing recommendations. The present invention conducts time-period dynamic analysis by integrating multi-dimensional behavior data of users, can fully grasp the product preference characteristics of users at a specific time period, master the products that users are interested in, effectively improve the accuracy of product recommendations for users, and significantly increase the recommendation conversion rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following-described drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 It is a schematic diagram of the steps of the method in Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of the composition of the system in Embodiment 2 of the present invention; Figure 3 It is a schematic diagram of the composition of the system in Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention. The specific structures and functional details disclosed herein are only used to describe the exemplary embodiments of the present invention. However, the present invention can be embodied in many alternative forms and should not be construed as limited to the embodiments described herein.

[0021] It should be understood that unless otherwise clearly specified and limited, the corresponding terms should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be directly connected, or indirectly connected through an intermediate medium, and can be the internal communication of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments can be understood according to specific situations.

[0022] Specific details are provided in the following description to facilitate a complete understanding of the exemplary embodiments. However, those of ordinary skill in the art should understand that the exemplary embodiments can be implemented without these specific details. For example, the device may be shown in a block diagram to avoid obscuring the example with unnecessary details. In other embodiments, well-known processes, structures, and techniques may not be shown with non-essential details to avoid obscuring the embodiments.

[0023] Embodiment 1: This embodiment provides a marketing method based on user behavior analysis, which can be applied to a corresponding marketing platform, such as Figure 1 As shown, the method includes the following steps: S1. Collect the historical behavior data sets of the target user for various products within a set time period. The historical behavior data sets include historical search term frequency data, historical browsing duration data, historical purchase price data, and historical purchase frequency data.

[0024] In specific implementation, the platform first collects the historical behavior data sets of the target user for various products within a set time period (such as within the past 30 days). The historical behavior data sets include historical search term frequency data (i.e., the historical search term frequency for keywords of a certain type of product), historical browsing duration data (i.e., the historical browsing duration for a certain type of product), historical purchase price data (i.e., the historical purchase price for a certain type of product), and historical purchase frequency data (i.e., the historical purchase frequency for a certain type of product).

[0025] S2. Determine the search frequency factors for various products according to the historical search term frequency data of the target user for various products, and calculate the search frequency index parameters for various products by using the search frequency factors for various products.

[0026] In specific implementation, the platform first determines the ratio of the historical search term frequency data of the target user for a certain type of product to the sum of the historical search term frequency data of all types of products, and then uses this ratio as the search frequency factor for the certain type of product. Then, the search frequency index parameters for various products are obtained by multiplying the search frequency factors for each certain type of product by a set search index coefficient.

[0027] S3. Determine the browsing duration factors for various products according to the historical browsing duration data of the target user for various products, and calculate the browsing duration index parameters for various products by using the browsing duration factors for various products.

[0028] During specific implementation, the platform first determines the ratio of the historical browsing duration data of the target user for a certain type of product to the sum of the historical browsing duration data for all types of products, and then uses this ratio as the browsing duration factor for the certain type of product. Then, the browsing duration factors of various types of products are substituted into a preset arithmetic formula for browsing duration index parameters for calculation to obtain the browsing duration index parameters of various types of products. The arithmetic formula for the browsing duration index parameters is as follows:

[0029] where i represents the product category number, T i represents the browsing duration index parameter of the i-th type of product, t i represents the browsing duration factor of the i-th type of product, τ is a set duration index coefficient, and tanh is the hyperbolic tangent function.

[0030] S4. Determine the purchase price factors of various types of products based on the historical purchase price data of the target user for various types of products, and calculate the price preference index parameters of various types of products using the purchase price factors of various types of products.

[0031] During specific implementation, the platform first determines the platform benchmark price data of various types of products, and takes the absolute value of the difference between the historical purchase price data of the target user for a certain type of product and the platform benchmark price data of this type of product as the purchase price factor of this type of product. Then, the purchase price factors of various types of products are substituted into a preset arithmetic formula for price preference index parameters for calculation to obtain the price preference index parameters of various types of products. The arithmetic formula for the price preference index parameters is as follows:

[0032] where i represents the product category number, P i represents the price preference index parameter of the i-th type of product, p i represents the purchase price factor of the i-th type of product, and σ is a set price index coefficient.

[0033] S5. Determine the purchase frequency factors of various types of products based on the historical purchase frequency data of the target user for various types of products, and calculate the purchase propensity index parameters of various types of products using the purchase frequency factors of various types of products.

[0034] During specific implementation, the platform first determines the ratio of the historical purchase frequency data of the target user for a certain type of product to the sum of the historical purchase frequency data for all types of products, and then uses this ratio as the purchase frequency factor of the certain type of product. Then, the purchase frequency factors of various types of products of the target user are substituted into a preset arithmetic formula for purchase propensity index parameters for calculation to obtain the purchase propensity index parameters of various types of products. The arithmetic formula for the purchase propensity index parameters is as follows:

[0035] Among them, i represents the product category number, N i represents the purchase tendency index parameter of the i-th type of product, and n i represents the purchase frequency factor of the i-th type of product, and δ is the set frequency index coefficient.

[0036] S6. Calculate the dynamic recommendation index of each type of product based on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase tendency index parameter.

[0037] Specifically in implementation, the platform performs weighted summation calculation on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase tendency index parameter of a certain type of product to obtain the dynamic recommendation index of this type of product.

[0038] S7. Screen out the marketing recommended products from each type of product according to the dynamic recommendation index of each type of product, and push the product information of the marketing recommended products to the target users.

[0039] Specifically in implementation, the platform screens out several types of products with the highest dynamic recommendation index from each type of product as the marketing recommended products, then retrieves the product information of each marketing recommended product, and pushes the product information of the marketing recommended products to the target users to achieve precise product marketing recommendations.

[0040] The method of this embodiment comprehensively performs time period dynamic analysis on the multi-dimensional behavior data of users, can fully grasp the product preference characteristics of users in a specific time period, master the products that users are interested in, effectively improve the accuracy of product recommendations for users, and significantly improve the recommendation conversion rate.

[0041] Embodiment 2: This embodiment provides a marketing system based on user behavior analysis, such as Figure 2 shown, including a data collection unit, a first determination unit, a second determination unit, a third determination unit, a fourth determination unit, an index calculation unit, and a marketing push unit, where: The data collection unit is used to collect the historical behavior data set of the target user for various types of products within a set time period, and the historical behavior data set includes historical search term frequency data, historical browsing duration data, historical purchase price data, and historical purchase frequency data; The first determination unit is used to determine the search frequency factor of each type of product according to the historical search term frequency data of the target user for various types of products, and calculate the search frequency index parameter of each type of product by using the search frequency factor of each type of product; The second determination unit is used to determine the browsing duration factor of each type of product according to the historical browsing duration data of the target user for various types of products, and calculate the browsing duration index parameter of each type of product by using the browsing duration factor of each type of product; A third determination unit, configured to determine a purchase price factor for each type of product based on the historical purchase price data of the target user for each type of product, and calculate a price preference index parameter for each type of product by using the purchase price factor for each type of product; A fourth determination unit, configured to determine a purchase frequency factor for each type of product based on the historical purchase frequency data of the target user for each type of product, and calculate a purchase propensity index parameter for each type of product by using the purchase frequency factor for each type of product; An index calculation unit, configured to calculate a dynamic recommendation index for each type of product based on a search frequency index parameter, a browsing duration index parameter, a price preference index parameter, and a purchase propensity index parameter; A marketing push unit, configured to screen marketing recommended products from each type of product according to the dynamic recommendation index of each type of product, and push product information of the marketing recommended products to the target user.

[0042] Embodiment 3: This embodiment provides a marketing system based on user behavior analysis. As Figure 3 shown, at the hardware level, it includes: A data interface, configured to establish data docking between the processor and an external data terminal; A memory, configured to store instructions; A processor, configured to read instructions stored in the memory and execute the marketing method based on user behavior analysis in Embodiment 1 according to the instructions.

[0043] Optionally, the system further includes an internal bus, and the processor, the memory, and the data interface can be interconnected through the internal bus. The internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0044] The memory may but is not limited to include Random Access Memory (RAM), Read Only Memory (ROM), Flash Memory, First Input First Output (FIFO), and / or First In Last Out (FILO), etc. The processor may be a general-purpose processor, including Central Processing Unit (CPU), Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), Application Specific Integrated Circuit (ASIC), Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0045] Embodiment 4: This embodiment provides a computer-readable storage medium, on which instructions are stored. When the instructions run on a computer, the computer is caused to execute the marketing method based on user behavior analysis in Embodiment 1. Among them, the computer-readable storage medium refers to a carrier for storing data, and may but is not limited to include floppy disks, optical discs, hard disks, flash memories, USB flash drives, and / or Memory Sticks, etc. The computer may be a general computer, a special computer, a computer network, or other programmable devices.

[0046] This embodiment also provides a computer program product, which, when running on a computer, executes the marketing method based on user behavior analysis in Embodiment 1. Among them, the computer may be a general computer, a special computer, a computer network, or other programmable devices.

[0047] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A marketing method based on user behavior analysis, characterized in that Including: Collecting a historical behavior dataset of a target user for various products within a set time period, where the historical behavior dataset includes historical search frequency data, historical browsing duration data, historical purchase price data, and historical purchase frequency data; Determining a search frequency factor for each type of product based on the historical search frequency data of the target user for each type of product, and calculating a search frequency index parameter for each type of product using the search frequency factor of each type of product; Determining a browsing duration factor for each type of product based on the historical browsing duration data of the target user for each type of product, and calculating a browsing duration index parameter for each type of product using the browsing duration factor of each type of product; Determining a purchase price factor for each type of product based on the historical purchase price data of the target user for each type of product, and calculating a price preference index parameter for each type of product using the purchase price factor of each type of product; Determining a purchase frequency factor for each type of product based on the historical purchase frequency data of the target user for each type of product, and calculating a purchase tendency index parameter for each type of product using the purchase frequency factor of each type of product; Calculating a dynamic recommendation index for each type of product based on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase tendency index parameter; Screening marketing recommended products from various products according to the dynamic recommendation index of each type of product, and pushing the product information of the marketing recommended products to the target user.

2. The marketing method based on user behavior analysis according to claim 1, wherein The step of determining a search frequency factor for each type of product based on the historical search frequency data of the target user for each type of product, and calculating a search frequency index parameter for each type of product using the search frequency factor of each type of product includes: Determining the ratio of the historical search frequency data of the target user for a certain type of product to the sum of the historical search frequency data for all types of products, and taking this ratio as the search frequency factor of the certain type of product; Multiplying the search frequency factor of each certain type of product by a set search index coefficient respectively to obtain the search frequency index parameter of each type of product.

3. The marketing method based on user behavior analysis according to claim 1, characterized in that, The step of determining a browsing duration factor for each type of product based on the historical browsing duration data of the target user for each type of product, and calculating a browsing duration index parameter for each type of product using the browsing duration factor of each type of product includes: Determining the ratio of the historical browsing duration data of the target user for a certain type of product to the sum of the historical browsing duration data for all types of products, and taking this ratio as the browsing duration factor of the certain type of product; Substituting the browsing duration factor of each type of product into a preset browsing duration index parameter calculation formula for calculation to obtain the browsing duration index parameter of each type of product, and the browsing duration index parameter calculation formula is: Among them, i represents the product category number, T i represents the browsing duration index parameter of the i-th category of products, t i represents the browsing duration factor of the i-th category of products, τ is the set duration index coefficient, and tanh is the hyperbolic tangent function.

4. The marketing method based on user behavior analysis according to claim 1, wherein The step of determining a purchase price factor for each type of product based on the historical purchase price data of the target user for each type of product, and calculating a price preference index parameter for each type of product using the purchase price factor of each type of product includes: Determining the platform benchmark price data of each type of product, and taking the absolute value of the difference between the historical purchase price data of the target user for a certain type of product and the platform benchmark price data of this type of product as the purchase price factor of this type of product; Substitute the purchase price factors of various products into the preset price preference index parameter calculation formula for calculation to obtain the price preference index parameters of various products. The price preference index parameter calculation formula is as follows: Among them, i represents the product category number, and P i represents the price preference index parameter of the i-th type of product, and p i represents the purchase price factor of the i-th type of product, and σ is the set price index coefficient.

5. The marketing method based on user behavior analysis according to claim 1, characterized in that, Determine the purchase frequency factors of various products according to the historical purchase frequency data of the target user for various products, and calculate the purchase tendency index parameters of various products by using the purchase frequency factors of various products, including: Determine the ratio of the historical purchase frequency data of the target user for a certain type of product to the sum of the historical purchase frequency data of all types of products, and use this ratio as the purchase frequency factor of the certain type of product; Substitute the purchase frequency factors of various products into the preset purchase tendency index parameter calculation formula for calculation to obtain the purchase tendency index parameters of various products. The purchase tendency index parameter calculation formula is as follows: Among them, i represents the product category number, N i represents the purchase tendency index parameter of the i-th type of product, n i represents the purchase frequency factor of the i-th type of product, and δ is the set frequency index coefficient.

6. The marketing method based on user behavior analysis according to claim 1, wherein Calculate the dynamic recommendation index of various products based on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase tendency index parameter, including: Perform weighted summation on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase tendency index parameter of a certain type of product to obtain the dynamic recommendation index of the certain type of product.

7. The marketing method based on user behavior analysis according to claim 1, characterized in that Screen marketing recommendation products from various products according to the dynamic recommendation index of various products, including: Screen several types of products with the highest dynamic recommendation index from various products as marketing recommendation products.

8. A marketing system based on user behavior analysis, characterized in that, It includes a data collection unit, a first determination unit, a second determination unit, a third determination unit, a fourth determination unit, an index calculation unit, and a marketing push unit, where: The data collection unit is used to collect the historical behavior data set of the target user for various products within a set time period. The historical behavior data set includes historical search term frequency data, historical browsing duration data, historical purchase price data, and historical purchase frequency data; The first determination unit is used to determine the search frequency factors of various products according to the historical search term frequency data of the target user for various products, and calculate the search frequency index parameters of various products by using the search frequency factors of various products; The second determination unit is used to determine the browsing duration factors of various products according to the historical browsing duration data of the target user for various products, and calculate the browsing duration index parameters of various products by using the browsing duration factors of various products; The third determination unit is used to determine the purchase price factors of various products according to the historical purchase price data of the target user for various products, and calculate the price preference index parameters of various products by using the purchase price factors of various products; The fourth determination unit is used to determine the purchase frequency factors of various products according to the historical purchase frequency data of the target user for various products, and calculate the purchase tendency index parameters of various products by using the purchase frequency factors of various products; The index calculation unit is used to calculate the dynamic recommendation index of various products based on the search frequency index parameter, browsing duration index parameter, price preference index parameter, and purchase tendency index parameter; The marketing push unit is used to screen marketing recommendation products from various products according to the dynamic recommendation index of various products, and push the product information of the marketing recommendation products to the target user.

9. A marketing system based on user behavior analysis, characterized in that, It includes: A memory for storing instructions; A processor for reading the instructions stored in the memory and executing the marketing method based on user behavior analysis according to any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product runs on a computer, it executes the marketing method based on user behavior analysis according to any one of claims 1-7.

Images